String sessionId = "remove-with-archives";
        keyManager.storeSessionKey(sessionId, testKey, "AES");

        // Create archived versions
        for (int i = 0; i < 3; i++) {
            keyManager.rotateSessionKey(sessionId);
        }

        // Verify archives exist
        assertTrue(keyManager.hasSessionKey(sessionId + ".v0"), "Version 0 should exist");

            });

            // Keep only the specified number of versions
            for (int i = keepVersions; i < archives.size(); i++) {
                removeSessionKey(archives.get(i));
                removed++;
            }
        }

        if (removed > 0) {
            log.info("Cleaned up {} archived key versions", removed);
        }
    }

    private int extractVersion(String archivedKey) {

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files

import java.io.BufferedInputStream;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.archivers.zip.ZipArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ExtractData;

import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;

application/hep                hep              # Hummingbird Host Explorer Profiles
application/lotus-123          wks              # Lotus 123
application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File

/*
Package zip provides support for reading and writing ZIP archives.

See the [ZIP specification] for details.

This package does not support disk spanning.

A note about ZIP64:

To be backwards compatible the FileHeader has both 32 and 64 bit Size
fields. The 64 bit fields will always contain the correct value and
for normal archives both fields will be the same. For files requiring

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.
 * This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {

application/hep                hep              # Hummingbird Host Explorer Profiles
application/lotus-123          wks              # Lotus 123
application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File

# the maven-style src/main/java subdirectory.
#
# Bazel manages annotation generated source as follows: First, it
# calls javac with options that create generated files under a
# bazel-out directory. Next, it archives the generated source files
# into a srcjar directly under the root. There doesn't appear to be a
# simple way to parameterize this from bazel, hence this helper to
# "normalize" the srcjar layout.
#
# Arguments: